Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already declare read-only, idempotent, and non-destructive behavior, so the description is not required to restate them. It adds genuine behavioral context not in the annotations: the $0.25–$0.85 per-call cost drawn from Einstein credit balance and the existence of free alternatives. It could have added pagination or response-shape notes, but the output schema handles much of that.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact sentences: the first front-loads the full capability list, and the second delivers the cost and free-alternative caveat. No filler or duplicated schema text. The most decision-relevant information (scope, price, alternative) appears early.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given an output schema, optional parameters, and non-destructive annotations, the description covers the remaining essential context: cost, credit source, and where to find free alternatives. It does not explicitly tie each domain to a 'kind' value, but the enum and its descriptions are self-explanatory, so nothing critical is missing for selecting and invoking the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema description coverage, the baseline is strong, and the description adds meaning by expanding the enum values into concrete analysis intents: 'mempool and fee intelligence,' 'bridges comparison,' and 'Babylon staking.' It does not discuss the 'limit' parameter, but the schema already documents it with default and range, so the description does not need to compensate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific resource ('Bitcoin-native analysis') and enumerates the supported domains: mempool/fee intelligence, network/mining health, BRC-20, Runes, bridges, and staking. This maps cleanly to the 'kind' enum and separates it from the general analyze_wallet and other analyze_* siblings. It loses one point because the description says only 'analysis' and does not state what kind of result the caller gets (e.g., metrics, rankings, comparisons).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The paid-cost warning and pointer to list_einstein_capabilities for free alternatives is useful routing information and an implied when-not-to-use signal. However, it never explicitly tells the agent when to pick analyze_bitcoin over closely related siblings such as inspect_onchain or get_bitcoin_cycle_position, so usage guidance remains mostly implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.